Counterfactual Multi-Agent Policy Gradients

8 987
21.4
Опубликовано 28 августа 2017, 19:08
Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. In this talk, I overview some of the key challenges in developing reinforcement learning methods that can efficiently learn decentralised policies for such systems. I also propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents’ policies.  In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent’s action, while keeping the other agents’ actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. Finally, I present results evaluating COMA in the testbed of StarCraft unit micromanagement. 

See more on this video at microsoft.com/en-us/research/v...
Случайные видео
13.12.22 – 5 46314:35
Figuring out finicky 404s
25.01.21 – 36 9029:11
The future of autonomous systems
25.10.14 – 36 9582:38
LG G3 Vigor Unboxing
автотехномузыкадетское